Are AI agents the new machine translation frontier? Challenges and opportunities of single- and multi-agent systems for multilingual digital communication

TL;DR

The paper investigates whether AI agents, organized as single-agent or multi-agent workflows, can advance machine translation by improving domain adaptation and contextual awareness. It presents a theoretical framework for structuring agent-based MT and validates it with a pilot study in legal translation using a four-agent, parallel workflow. Results show that larger multi-agent configurations can outperform traditional NMT baselines in adequacy and fluency, suggesting tangible benefits for high-stakes domains and professional workflows. The authors also discuss practical implications, public tooling, and a roadmap for tool integration, scalability, evaluation, and human–AI collaboration in multilingual digital communication.

Abstract

The rapid evolution of artificial intelligence (AI) has introduced AI agents as a disruptive paradigm across various industries, yet their application in machine translation (MT) remains underexplored. This paper describes and analyses the potential of single- and multi-agent systems for MT, reflecting on how they could enhance multilingual digital communication. While single-agent systems are well-suited for simpler translation tasks, multi-agent systems, which involve multiple specialized AI agents collaborating in a structured manner, may offer a promising solution for complex scenarios requiring high accuracy, domain-specific knowledge, and contextual awareness. To demonstrate the feasibility of multi-agent workflows in MT, we are conducting a pilot study in legal MT. The study employs a multi-agent system involving four specialized AI agents for (i) translation, (ii) adequacy review, (iii) fluency review, and (iv) final editing. Our findings suggest that multi-agent systems may have the potential to significantly improve domain-adaptability and contextual awareness, with superior translation quality to traditional MT or single-agent systems. This paper also sets the stage for future research into multi-agent applications in MT, integration into professional translation workflows, and shares a demo of the system analyzed in the paper.

Figures (5)

• Figure 1: An example of single- and multi-agent systems applied to MT.
• Figure 2: Some potential customisations of multi-agent workflows.
• Figure 3: Multi-agent workflow analysed in the pilot study + demo.
• Figure 4: Fluency-Adequacy results.
• Figure 5: Ranking results.